Skip to main content

ORIGINAL RESEARCH article

Front. Energy Res.
Sec. Smart Grids
Volume 12 - 2024 | doi: 10.3389/fenrg.2024.1444697
This article is part of the Research Topic Enhancing Resilience in Smart Grids: Cyber-Physical Systems Security, Simulations, and Adaptive Defense Strategies View all 16 articles

Towards a More Secure Reconstruction-Based Anomaly Detection Model for Power Transformer Differential Protection

Provisionally accepted
Martiya Zare Jahromi Martiya Zare Jahromi 1*Mohsen Khalaf Mohsen Khalaf 1Marthe Kassouf Marthe Kassouf 2Deepa Kundur Deepa Kundur 1
  • 1 University of Toronto, Toronto, Canada
  • 2 Hydro-Québec’s Research Institute, IREQ, Varennes, Quebec, Canada

The final, formatted version of the article will be published soon.

    Cyberattacks against Power Transformer Differential Protection (PTDP) have the potential to cause significant disruption and widespread blackouts in power infrastructure. Recent literature has demonstrated how reconstruction-based anomaly detection models can play a critical role in enhancing the security of PTDP against such attacks. However, these models themselves are vulnerable to cyber threats. Adversarial sample generation is an example of a threat against reconstruction-based anomaly detection models. In this paper, to address this threat we propose an approach for adversarial training of such models appropriate for PTDPs. We then review and compare the effect of adversarial training on the performance of four different model architectures. To demonstrate the efficacy of our proposed approach for improved security and performance in PTDP scenarios, the IEEE PSRC D6 benchmark test system is tested in an OPAL-RT environment. Simulation results show the effectiveness of the proposed method for improved detection of cyberattacks.

    Keywords: Cyber-physical Systems, trustworthy machine learning, anomaly detection, transformer protective relays, Adversarial defense

    Received: 06 Jun 2024; Accepted: 28 Nov 2024.

    Copyright: © 2024 Zare Jahromi, Khalaf, Kassouf and Kundur. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Martiya Zare Jahromi, University of Toronto, Toronto, Canada

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.